Urban agglomeration waterlogging hazard exposure assessment based on an integrated Naive Bayes classifier and complex network analysis

Mo Wang (), Xiaoping Fu, Dongqing Zhang, Siwei Lou (), Jianjun Li (), Furong Chen, Shan Li and Soon Keat Tan
Additional contact information
Mo Wang: Guangzhou University
Xiaoping Fu: Guangzhou University
Dongqing Zhang: Guangdong University of Petrochemical Technology
Siwei Lou: Guangzhou University
Jianjun Li: Guangzhou University
Furong Chen: Guangzhou University
Shan Li: Guangzhou University
Soon Keat Tan: Nanyang Technological University

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2023, vol. 118, issue 3, No 16, 2173-2197

Abstract: Abstract Urban waterlogging can cause considerable economic damage, public inconvenience, and even mortality. Effective prediction of inundation probability on an urban agglomeration scale is an essential step in adaptation planning. This study proposes an urban waterlogging exposure assessment framework using the Weighted Naive Bayesian (WNB) classifier and a Complex Network Model (CNM). WNB classifier delineates the risk distribution projections by assimilating risk factors and empirical data of urban waterlogging events. This projection was subsequently validated using an overarching accuracy coefficient of 0.85 and a Kappa coefficient of 0.75, these numerical metrics serving as critical evaluative thresholds for the verification of the WNB model's efficacy and precision. CNM is used to analyze the composition and correlation of system risk attributes according to its network topology. We applied the proposed framework to the Guangdong-Hong Kong-Macao Greater Bay Area (GBA). We found that 20.0% of the study areas are exposed to waterlogging risk, of which 1.4% of the study areas are at high risk. There is a clear spatial concentration of urban waterlogging risks in the downtown area of populated cities. In addition, according to CNM, the urban waterlogging hazards of most townships are stressed by multiple factors such as fractional vegetation cover, impervious surface percentage, and soil water retention. The townships stressed by a single factor are attributed to the distance from the waterway or road density. The framework could provide in-depth insights into urban waterlogging preparedness and emergency response.

Keywords: Urban waterlog; Weighted Naive Bayesian; Spatial autocorrelation; Complex network model; Dominant factor (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-023-06118-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:118:y:2023:i:3:d:10.1007_s11069-023-06118-3

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-023-06118-3

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().